aitraining llm --train \
  --model meta-llama/Llama-3.2-1B \
  --data-path ./data \
  --project-name my-model \
  --trainer sft \
  --peft

aitraining llm --train \
  --model meta-llama/Llama-3.2-3B \
  --data-path ./data \
  --project-name my-model \
  --trainer sft \
  --distributed-backend deepspeed \
  --peft

from autotrain.trainers.clm.params import LLMTrainingParams
from autotrain.project import AutoTrainProject

params = LLMTrainingParams(
    model="meta-llama/Llama-3.2-3B",
    data_path="./data",
    project_name="distributed-model",

    trainer="sft",

    # Distribution
    distributed_backend="deepspeed",  # or None for DDP

    # Training
    epochs=3,
    batch_size=2,
    gradient_accumulation=4,
    mixed_precision="bf16",

    peft=True,
    lora_r=16,
)

project = AutoTrainProject(params=params, backend="local", process=True)
project.create()

task: llm-sft
backend: local
base_model: meta-llama/Llama-3.2-3B
project_name: distributed-model

data:
  path: ./data
  train_split: train
  valid_split: null
  chat_template: tokenizer
  column_mapping:
    text_column: text

log: wandb

params:
  distributed_backend: deepspeed  # or null for DDP
  epochs: 3
  batch_size: 2
  gradient_accumulation: 4
  mixed_precision: bf16
  peft: true
  lora_r: 16

# 在每个节点上
aitraining llm --train \
  --model meta-llama/Llama-3.2-3B \
  --data-path ./data \
  --project-name my-model \
  --distributed-backend deepspeed \
  --peft

# 使用特定 GPU
CUDA_VISIBLE_DEVICES=0,1 aitraining llm --train ...

# 使用所有可用 GPU（默认）
aitraining llm --train ...

accelerate env